Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3748 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2487. Min Act: -0.0000

Data Index: 684521 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2470. Min Act: -0.0000

Data Index: 83932 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1314293 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2233. Min Act: -0.0000

Data Index: 14539 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1691211 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2097. Min Act: -0.0000

Data Index: 499726 (The Pile)

Max Activating Token Index: 134

Text #6

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2320. Min Act: -0.0000

Data Index: 568648 (The Pile)

Max Activating Token Index: 867

Text #7

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2129. Min Act: -0.0000

Data Index: 306322 (The Pile)

Max Activating Token Index: 194

Text #8

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2264. Min Act: -0.0000

Data Index: 871215 (The Pile)

Max Activating Token Index: 264

Text #9

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1947. Min Act: -0.0000

Data Index: 471010 (The Pile)

Max Activating Token Index: 870

Text #10

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2087. Min Act: -0.0000

Data Index: 625384 (The Pile)

Max Activating Token Index: 476

Text #11

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1066765 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2108. Min Act: -0.0000

Data Index: 648776 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1972721 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1894. Min Act: -0.0000

Data Index: 365770 (The Pile)

Max Activating Token Index: 576

Text #15

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1756. Min Act: -0.0000

Data Index: 258835 (The Pile)

Max Activating Token Index: 69

Text #16

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1430188 (The Pile)

Max Activating Token Index: 561

Text #17

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1964. Min Act: -0.0000

Data Index: 989596 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1185117 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1799843 (The Pile)

Max Activating Token Index: 646